New energy automobile endurance mileage online prediction method and system

By analyzing the historical vehicle data of new energy vehicles, establishing an energy consumption and characteristic matrix of 100 kilometers, and personalizing predictions based on battery status, the problem of inaccurate range prediction in the existing technology is solved, and the accuracy of prediction is improved and User experience.

CN118977576APending Publication Date: 2024-11-19JIANGLING MOTORS
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411328487.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-24
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

The existing range prediction methods for new energy vehicles are not accurate enough, especially when the battery is aging and the actual driving conditions are different, which can easily lead to power exhaustion and increase user anxiety in using the car.

Method used

By obtaining the vehicle condition data of multiple historical vehicles, counting the energy consumption matrix and feature matrix of 100 kilometers, personalizing energy consumption prediction based on the battery status of the target vehicle, and correcting the energy consumption characteristic value to improve prediction accuracy.

Benefits of technology

It realizes accurate prediction of the range of new energy vehicles in pure electric mode, reduces the risk of power exhaustion during driving, alleviates user anxiety, and improves the accuracy and reliability of predictions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118977576A_ABST
    Figure CN118977576A_ABST
Patent Text Reader

Abstract

The invention discloses a new energy vehicle endurance mileage online prediction method and system, and belongs to the technical field of vehicle endurance prediction, and the method comprises the steps: obtaining a hundred-kilometer energy consumption average value of each SOH interval between a starting SOH and a preset termination SOH of a plurality of vehicles, and forming a hundred-kilometer energy consumption matrix A; taking a characteristic representative number for each column of SOH values of A to form a hundred-kilometer energy consumption characteristic matrix B; if the SOH value of the battery pack of the target vehicle is smaller than a preset SOH value, counting a hundred-kilometer energy consumption average value of the target vehicle from the initial SOH to the current SOH to obtain a target hundred-kilometer energy consumption matrix D, obtaining a difference value between the target hundred-kilometer energy consumption matrix D and B to obtain a use characteristic matrix E, fitting to obtain a use characteristic value F, and correcting B to obtain a second target hundred-kilometer energy consumption prediction matrix C2; and obtaining the current or predicted total endurance mileage of the target vehicle according to C1 or C2. According to the method, the endurance mileage of the new energy vehicle in the pure electric mode can be accurately predicted, the new energy vehicle is prevented from lying down in the driving process, and the vehicle using anxiety of a user is relieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of vehicle cruising range prediction, and in particular relates to an online prediction method and system for the cruising range of a new energy vehicle. Background Art

[0002] As the world pays more and more attention to environmental protection and sustainable development, new energy vehicles, as a green and low-carbon means of transportation, have developed rapidly. However, the range of new energy vehicles has always been one of the bottlenecks restricting their widespread application. In actual use, the range of new energy vehicles is affected by many factors, such as vehicle speed, acceleration, driving conditions, ambient temperature, humidity, wind speed and atmospheric pressure. Therefore, how to accurately predict the range of new energy vehicles is of great significance to improving user experience and promoting the popularization of new energy vehicles.

[0003] The mileage calculation displayed by many new energy vehicles is based on the mileage obtained by the CLTC (China Light Vehicle Condition Test) test, and then multiplied by the remaining power percentage to estimate. In the early days of new energy vehicles, this method can provide a certain reference for drivers. However, as the battery ages, this calculation method often causes the displayed mileage value to be much higher than the actual drivable mileage, which is misleading. In addition, due to differences in actual driving conditions and driving behaviors (such as acceleration, deceleration, driving speed, external environment, etc.), the mileage provided by this calculation method is even more unreliable, and may even cause the vehicle to run out of power during driving. Therefore, accurately predicting the mileage of new energy vehicles in pure electric mode and avoiding the breakdown of new energy vehicles during driving can alleviate users' anxiety about using cars. Summary of the invention

[0004] Based on this, the present application proposes an online prediction method and system for the cruising range of new energy vehicles, aiming to accurately predict the cruising range of new energy vehicles in pure electric mode, avoid the new energy vehicle breaking down during driving, and alleviate users' anxiety about using the vehicle.

[0005] The first aspect of the present application provides an online prediction method for the cruising range of a new energy vehicle, the method comprising: Obtain vehicle condition data of multiple historical vehicles; According to the vehicle condition data, the average energy consumption per 100 kilometers of each historical vehicle in each preset SOH interval from the SOH start value to the preset SOH end value is counted to form a 100-kilometer energy consumption matrix A; the characteristic representative number is taken for each column of the SOH value of the 100-kilometer energy consumption matrix A to form a 100-kilometer energy consumption characteristic matrix B; Obtain the battery pack SOH value of the target vehicle, and determine the relationship between the battery pack SOH value and the preset battery SOH value: If the battery pack SOH value is greater than or equal to the preset battery SOH value, the 100-kilometer energy consumption characteristic matrix B is used as the first target 100-kilometer energy consumption prediction matrix C1; If the battery pack SOH value is less than the preset battery SOH value, the average energy consumption per 100 kilometers of the target vehicle in each preset SOH interval from the SOH starting value to the SOH current value is counted to obtain a target energy consumption matrix D per 100 kilometers; the difference between the energy consumption characteristic matrix B per 100 kilometers and the target energy consumption matrix D per 100 kilometers is taken to obtain a usage characteristic matrix E, and the values ​​in the usage characteristic matrix E are fitted to obtain a usage characteristic value F; the energy consumption characteristic matrix B per 100 kilometers is corrected using the characteristic value F to obtain a second target energy consumption prediction matrix C2 per 100 kilometers; According to the target 100-kilometer energy consumption prediction matrix, the current cruising range value or the predicted total cruising range of the target vehicle is obtained, and the target 100-kilometer energy consumption prediction matrix is ​​the first target 100-kilometer energy consumption prediction matrix C1 or the second target 100-kilometer energy consumption prediction matrix C2.

[0006] Compared with the prior art, the present application provides an online prediction method for the cruising range of new energy vehicles. The method obtains vehicle condition data of multiple historical vehicles, and based on these data, statistics the average 100-kilometer energy consumption of each vehicle at each preset SOH interval from the SOH start value to the preset SOH end value to form a 100-kilometer energy consumption matrix A, so that a 100-kilometer energy consumption database of historical vehicles can be established; the characteristic representative number is taken for each column of the SOH value of the 100-kilometer energy consumption matrix A to form a 100-kilometer energy consumption characteristic matrix B, so that characteristic data of the 100-kilometer energy consumption changing with SOH can be extracted to provide a basis for subsequent predictions; if the battery pack SOH value of the target vehicle is greater than or equal to the preset battery SOH value, the 100-kilometer energy consumption characteristic matrix B is directly used as the first target 100-kilometer energy consumption prediction matrix C1, then it is considered that the target vehicle is in the current battery state, and its energy consumption characteristics are similar to the energy consumption characteristics of historical vehicles in similar SOH states ... If the H value is less than the preset battery SOH value, the average energy consumption per 100 kilometers of the target vehicle within the specific SOH range is calculated to form a target energy consumption matrix D for 100 kilometers, and the difference between matrix B and matrix D is taken to obtain the usage characteristic matrix E, and then the values ​​in matrix E are fitted to obtain the usage eigenvalues ​​F. These eigenvalues ​​F are used to correct the energy consumption characteristic matrix B for 100 kilometers to obtain the second target energy consumption prediction matrix C2 for 100 kilometers. This series of steps takes into account the energy consumption changes of the target vehicle under a specific battery state and corrects it to improve the prediction certainty; according to the target energy consumption prediction matrix for 100 kilometers (whether it is the first target energy consumption prediction matrix C1 or the second target energy consumption prediction matrix C2), the current cruising range value or the predicted total cruising range of the target vehicle can be obtained. This step is based on the analysis and processing of a large amount of historical data and the consideration of the current state of the target vehicle to predict the energy consumption of the target vehicle, thereby accurately predicting its cruising range.

[0007] As an optional implementation manner of the first aspect, the vehicle condition data includes region, season, vehicle series, mileage, driving start and end time, battery pack voltage and current.

[0008] As an optional implementation manner of the first aspect, according to the vehicle condition data, the step of calculating the average energy consumption per 100 kilometers of each historical vehicle at each preset SOH interval from the SOH start value to the preset SOH end value includes: Determine the relationship between the mileage in the vehicle condition data and the preset mileage: If the mileage is less than the preset mileage, the vehicle condition data will be discarded; If the mileage is greater than or equal to the preset mileage, the vehicle condition data is used to classify the data by region, season, and vehicle series. The average energy consumption per 100 kilometers of each historical vehicle in each preset SOH interval from the SOH start value to the preset SOH end value is calculated according to the average energy consumption per 100 kilometers calculation formula. The average energy consumption per 100 kilometers calculation formula is: , Among them, u represents the average energy consumption per 100 kilometers, t1 and t0 represent the start and end time of driving respectively, V represents the battery pack voltage, I represents the battery pack current, and x represents the mileage.

[0009] As an optional implementation of the first aspect, the preset SOH interval is 1%.

[0010] As an optional implementation manner of the first aspect, when taking the characteristic representative number for each column of the SOH value of the 100-kilometer energy consumption matrix A, the median, mean or standard deviation is used as the characteristic representative number.

[0011] As an optional implementation of the first aspect, when fitting the values ​​in the characteristic matrix E to obtain the characteristic value F, the fitting calculation formula is F = (D - B) / B; When the eigenvalue F is used to correct the 100-kilometer energy consumption characteristic matrix B and obtain the second target 100-kilometer energy consumption prediction matrix C2, the corrected calculation formula is C2 = B * (1 + F).

[0012] As an optional implementation manner of the first aspect, in the step of obtaining the current cruising range value or predicted total cruising range of the target vehicle according to the target energy consumption prediction matrix per 100 kilometers, the current cruising range = (SOH×rated energy×SOC) / target energy consumption prediction value per 100 kilometers, and the total cruising range = (SOH×rated energy) / target energy consumption prediction value per 100 kilometers.

[0013] A second aspect of an embodiment of the present application provides an online prediction system for the cruising range of a new energy vehicle, the system comprising: A data acquisition module is used to acquire vehicle condition data of multiple historical vehicles; The data processing module is used to count the average energy consumption per 100 kilometers of each historical vehicle in each preset SOH interval from the SOH start value to the preset SOH end value according to the vehicle condition data, so as to form a 100-kilometer energy consumption matrix A; take the characteristic representative number of each column of the SOH value of the 100-kilometer energy consumption matrix A to form a 100-kilometer energy consumption characteristic matrix B; obtain the battery pack SOH value of the target vehicle, and determine the size relationship between the battery pack SOH value and the preset battery SOH value: A prediction module is used to use the 100-kilometer energy consumption characteristic matrix B as the first target 100-kilometer energy consumption prediction matrix C1 when the battery pack SOH value is greater than or equal to the preset battery SOH value; when the battery pack SOH value is less than the preset battery SOH value, the average 100-kilometer energy consumption of the target vehicle in each preset SOH interval from the SOH starting value to the host SOH current value is counted to obtain a target 100-kilometer energy consumption matrix D; the difference between the 100-kilometer energy consumption characteristic matrix B and the target 100-kilometer energy consumption matrix D is taken to obtain a usage characteristic matrix E, and the values ​​in the usage characteristic matrix E are fitted to obtain a usage characteristic value F; the 100-kilometer energy consumption characteristic matrix B is corrected using the characteristic value F to obtain a second target 100-kilometer energy consumption prediction matrix C2; according to the target 100-kilometer energy consumption prediction matrix, the current cruising range value or the predicted total cruising range of the target vehicle is obtained, and the target 100-kilometer energy consumption prediction matrix is ​​the first target 100-kilometer energy consumption prediction matrix C1 or the second target 100-kilometer energy consumption prediction matrix C2.

[0014] A third aspect of an embodiment of the present application provides a computer device, which includes a memory, a processor, and a processing program stored in the memory and executable on the processor, wherein the processing program, when executed by the processor, implements the above-mentioned online prediction method for the cruising range of a new energy vehicle.

[0015] A fourth aspect of an embodiment of the present application provides a storage medium, on which a processing program is stored. When the processing program is executed by a processor, the above-mentioned online prediction method for the cruising range of a new energy vehicle is executed.

[0016] Additional aspects and advantages of the present application will be given in part in the following description, and in part will become apparent from the following description, or will be understood through the embodiments of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a flow chart of an online prediction method for the cruising range of a new energy vehicle proposed in the first embodiment of the present application; Figure 2 A flowchart of an online prediction method for the cruising range of a new energy vehicle proposed in the second embodiment of the present application; Figure 3 This is a representation diagram of the energy consumption matrix A per 100 kilometers in the second implementation of this application; Figure 4 This is a representation of the energy consumption characteristic matrix B per 100 kilometers in the second implementation of this application; Figure 5 This is a representation of the target 100-kilometer energy consumption matrix D in the second implementation of this application; Figure 6 This is a representation diagram of the feature matrix E used in the second implementation of the present application; Figure 7 This is a diagram showing the representation of the characteristic value F used in the second implementation of the present application; Figure 8 This is a representation of the target 100-kilometer energy consumption prediction matrix C in the second implementation of this application; Fig. 9 This is a schematic diagram of the structure of an online prediction system for the cruising range of new energy vehicles proposed in the third embodiment of the present application.

[0018] The following specific implementation methods will further illustrate the present application in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0020] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here. In addition, the "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally represents that the objects associated with each other are in an "or" relationship.

[0021] In order to illustrate the technical solution described in this application, a specific embodiment is provided below for illustration.

[0022] See also Figure 1 , is a flow chart of an online prediction method for the cruising range of a new energy vehicle proposed in the first embodiment of the present application, and the proposed method includes: S01: Obtain vehicle condition data of multiple historical vehicles, and based on the vehicle condition data, calculate the average energy consumption per 100 kilometers of each historical vehicle at each preset SOH interval from the SOH start value to the preset SOH end value to form a 100-kilometer energy consumption matrix A; take a characteristic representative number for each column of the SOH value of the 100-kilometer energy consumption matrix A to form a 100-kilometer energy consumption characteristic matrix B.

[0023] It should be noted that SOH (State of Health) refers to the ratio of the remaining capacity of a battery to its original capacity, which is usually used to evaluate the performance and life of the battery; the SOH starting value and the preset SOH ending value are pre-set ranges of SOH values, which are used to determine the specific interval of analysis. The SOH starting value is usually 100%, and the preset SOH ending value can be 80% or 75%; the preset SOH interval means that within this range, the SOH value is divided into several equally spaced sub-intervals, which is used to analyze energy consumption changes in more detail; dimensions such as region, quarter, and vehicle series are used to group data to facilitate analysis of energy consumption under different conditions.

[0024] Specifically, the step S01 includes: S011: Data cleaning; First, obtain the vehicle condition data. For example, the vehicle condition data includes region, season, car series, mileage, driving start and end time, battery pack voltage and current. After obtaining the vehicle condition data, data cleaning is required. This is because in the actual data collection process, there may be outliers, missing values ​​or erroneous data. These data may have an adverse effect on the statistical results, so they need to be cleaned before processing the data.

[0025] S012: Data screening; Next, the vehicle condition data is filtered according to the preset mileage. If the mileage of a vehicle is less than the preset mileage, the data of the vehicle may be considered unrepresentative or of poor quality, and thus discarded. If the mileage is greater than or equal to the preset mileage, the data is considered to be of high quality and representativeness and can be used for subsequent analysis and calculations. S013: Data classification; After data screening, the vehicle condition data is classified according to dimensions such as region, season, and car series. In addition, in other embodiments, the dimensions for classifying vehicle condition data are not limited to region, season, and car series. This can make subsequent analysis more detailed and targeted. For example, the region may affect the driving environment and road conditions of the vehicle, the season may affect the frequency and intensity of vehicle use, and the car series directly affects the performance and energy consumption of the vehicle.

[0026] S014: Calculate the average energy consumption per 100 kilometers; For each historical vehicle, the energy consumption average value per 100 kilometers is calculated using the formula for calculating the energy consumption average value within each preset SOH interval between the SOH start value and the preset SOH end value.

[0027] The calculation formula for the average energy consumption per 100 kilometers is: , Among them, u represents the average energy consumption per 100 kilometers, t1 and t0 represent the start and end time of driving respectively, V represents the battery pack voltage, I represents the battery pack current, and x represents the mileage.

[0028] This formula takes into account driving time, battery pack voltage and current, and mileage, and can more accurately reflect the energy consumption of the vehicle under specific conditions.

[0029] S015: forming a 100-kilometer energy consumption matrix A; Through the above calculation, the average energy consumption per 100 kilometers of each historical vehicle at the preset SOH interval can be obtained to form a matrix A. Each row of the matrix A represents a vehicle, and each column represents a specific SOH value or interval.

[0030] S016: forming a 100-kilometer energy consumption characteristic matrix B; For each column of matrix A (i.e., each SOH value or interval), a characteristic representative number is selected to form a 100-kilometer energy consumption characteristic matrix B. The selection of characteristic representative numbers can be based on actual needs and analysis purposes. For example, the mean, median, standard deviation, etc. of a column can be selected.

[0031] S02: Obtaining the SOH value of the battery pack of the target vehicle, and determining the magnitude relationship between the SOH value of the battery pack and the preset battery SOH value; It should be noted that the purpose of obtaining the battery pack SOH (State of Health) value of the target vehicle is to evaluate the health status of the battery. The SOH value usually indicates the ratio of the remaining capacity of the battery to its rated capacity, reflecting the aging degree and performance of the battery. Therefore, judging the relationship between the battery pack SOH value and the preset battery SOH value can help us understand whether the current battery performance meets the expected standards, thereby determining the subsequent energy consumption prediction strategy.

[0032] S03: If the battery pack SOH value is greater than or equal to the preset battery SOH value, the 100-kilometer energy consumption characteristic matrix B is used as the first target 100-kilometer energy consumption prediction matrix C1.

[0033] It should be noted that if the battery pack SOH value is greater than or equal to the preset battery SOH value, it means that the battery performance is good and can effectively support the energy consumption requirements of the vehicle. In this case, directly using the 100-kilometer energy consumption characteristic matrix B as the first target 100-kilometer energy consumption prediction matrix C1 can ensure the accuracy and reliability of the prediction results. At this time, the battery performance will not have a significant impact on energy consumption.

[0034] S04: If the battery pack SOH value is less than the preset battery SOH value, then the average energy consumption per 100 kilometers of the target vehicle in each preset SOH interval from the SOH starting value to the SOH current value is calculated to obtain the target 100-kilometer energy consumption matrix D; the difference between the 100-kilometer energy consumption characteristic matrix B and the target 100-kilometer energy consumption matrix D is taken to obtain the usage characteristic matrix E, and the values ​​in the usage characteristic matrix E are fitted to obtain the usage eigenvalue F; the eigenvalue F is used to correct the 100-kilometer energy consumption characteristic matrix B to obtain the second target 100-kilometer energy consumption prediction matrix C2.

[0035] It should be noted that if the battery pack SOH value is less than the preset battery SOH value, it indicates that the battery performance has declined, which may lead to increased energy consumption. Therefore, it is necessary to obtain the target 100-kilometer energy consumption matrix D by counting the average energy consumption per 100 kilometers at each preset SOH interval from the SOH starting value to the current value, in order to consider the changes in energy consumption of the battery at different stages of use. The difference between the 100-kilometer energy consumption characteristic matrix B and the target 100-kilometer energy consumption matrix D is taken to obtain the usage characteristic matrix E, in order to highlight the energy consumption differences of the battery at different stages of use. The values ​​in the usage characteristic matrix E are fitted to obtain the usage characteristic value F, in order to establish the relationship between the battery usage characteristics and the energy consumption per 100 kilometers. The eigenvalue F is used to correct the 100-kilometer energy consumption characteristic matrix B to obtain the second target 100-kilometer energy consumption prediction matrix C2, in order to correct the 100-kilometer energy consumption according to the actual use of the battery and improve the accuracy of the prediction.

[0036] Specifically, when the values ​​in the characteristic matrix E are fitted to obtain the eigenvalue F, the fitting calculation formula is F = (D - B) / B; when the eigenvalue F is used to correct the 100-kilometer energy consumption characteristic matrix B to obtain the second target 100-kilometer energy consumption prediction matrix C2, the corrected calculation formula is C2 = B * (1 + F).

[0037] S05: Obtaining the current cruising range value or the predicted total cruising range of the target vehicle according to the target 100-kilometer energy consumption prediction matrix, wherein the target 100-kilometer energy consumption prediction matrix is ​​the first target 100-kilometer energy consumption prediction matrix C1 or the second target 100-kilometer energy consumption prediction matrix C2.

[0038] It should be noted that the current cruising range value or predicted total cruising range of the target vehicle is obtained based on the target 100-kilometer energy consumption prediction matrix in order to let users understand the vehicle's cruising range and remaining cruising range in the current state, so as to make reasonable travel plans. The calculation formula for the current cruising range is: current cruising range = (SOH × rated energy × SOC) / target 100-kilometer energy consumption prediction value; the calculation formula for the total cruising range is: total cruising range = (SOH × rated energy) target / 100-kilometer energy consumption prediction value. Among them, SOH is the health status of the battery, the rated energy is the rated capacity of the battery, SOC is the state of charge of the battery, and the target 100-kilometer energy consumption prediction value is the predicted 100-kilometer energy consumption value of the target vehicle in the current state, which is the sub-data in the target 100-kilometer energy consumption prediction matrix.

[0039] In summary, this method obtains the vehicle condition data of multiple historical vehicles and performs statistical analysis to form a 100-kilometer energy consumption matrix A and a 100-kilometer energy consumption characteristic matrix B, which provides a data basis for the target vehicle's cruising range prediction; compares the battery pack SOH value with the preset battery SOH value, and selects the 100-kilometer energy consumption characteristic matrix B or the corrected 100-kilometer energy consumption characteristic matrix B to predict the target 100-kilometer energy consumption according to the comparison result, thereby improving the accuracy and adaptability of the prediction; obtains the usage eigenvalue F by fitting the values ​​in the usage characteristic matrix E, and uses the usage eigenvalue F to correct the 100-kilometer energy consumption characteristic matrix B, thereby further improving the accuracy of the target 100-kilometer energy consumption prediction matrix; finally, the current cruising range value or the predicted total cruising range of the target vehicle is obtained according to the target 100-kilometer energy consumption prediction matrix, thereby providing an important reference for vehicle cruising range management and use.

[0040] See also Figure 2 , which is a flow chart of an online prediction method for a new energy vehicle cruising range proposed in the third embodiment of the present application, the method comprising: S001: Obtain historical data of n vehicles, pre-process and classify the historical data, and specifically count the average energy consumption per 100 kilometers of vehicles in Beijing, January to March, light trucks, and with a single mileage greater than or equal to 30 km; S002: Set the SOH value range to 100% to 80%, classify the SOH values ​​calculated by the model, and write them into the 100-kilometer energy consumption matrix A; For example, the model may be a battery quasi-two-dimensional model (P2D) and / or an equivalent circuit model ECM and / or a deep neural network model (DNN), etc. The representation of the energy consumption matrix A per 100 kilometers can be found in Figure 3 shown.

[0041] S003: Take the median of each column of the 100-kilometer energy consumption matrix A to obtain the 100-kilometer energy consumption characteristic matrix B; Similarly, the representation of the energy consumption characteristic matrix B per 100 km can be found in Figure 4 as shown. S004: If the current SOH value of the Beijing vehicle is greater than 98% of the preset battery SOH value, the operation is performed as in steps S002 and S003 to obtain the target 100 km energy consumption matrix D; Similarly, the target 100-kilometer energy consumption matrix D can be expressed in the form of Figure 5 shown.

[0042] S005: subtracting the 100-kilometer energy consumption characteristic matrix B from the target 100-kilometer energy consumption matrix D to obtain a usage characteristic matrix E, and fitting the values ​​in the usage characteristic matrix E to obtain a usage characteristic value F; Similarly, the representation using the feature matrix E can be found in Figure 6 As shown, the representation using the eigenvalue F can be found in Figure 7 shown.

[0043] S006: Correcting the 100-kilometer energy consumption characteristic matrix B by using the eigenvalue F to obtain the target 100-kilometer energy consumption prediction matrix C; Similarly, the target 100-kilometer energy consumption prediction matrix C can be expressed in the form of Figure 8 shown.

[0044] S007: Based on the current Beijing vehicle battery pack target energy consumption per 100 kilometers prediction matrix C, the current cruising range value is obtained by SOH×rated energy×SOC / target energy consumption prediction value per 100 kilometers, and the predicted total cruising range is obtained by SOH×rated energy / target energy consumption prediction value per 100 kilometers.

[0045] See also Fig. 9 , which is a schematic diagram of the structure of an online prediction system for the cruising range of a new energy vehicle proposed in the third embodiment of the present application, and the system includes: A data acquisition module 10 is used to acquire vehicle condition data of multiple historical vehicles; The data processing module 20 is used to count the average energy consumption per 100 kilometers of each historical vehicle in each preset SOH interval from the SOH start value to the preset SOH end value according to the vehicle condition data, so as to form a 100-kilometer energy consumption matrix A; take the characteristic representative number of each column of the SOH value of the 100-kilometer energy consumption matrix A to form a 100-kilometer energy consumption characteristic matrix B; obtain the battery pack SOH value of the target vehicle, and determine the size relationship between the battery pack SOH value and the preset battery SOH value: The prediction module 30 is used to use the 100-kilometer energy consumption characteristic matrix B as the first target 100-kilometer energy consumption prediction matrix C1 when the battery pack SOH value is greater than or equal to the preset battery SOH value; when the battery pack SOH value is less than the preset battery SOH value, the average 100-kilometer energy consumption of the target vehicle in each preset SOH interval from the SOH starting value to the host SOH current value is counted to obtain the target 100-kilometer energy consumption matrix D; the difference between the 100-kilometer energy consumption characteristic matrix B and the target 100-kilometer energy consumption matrix D is taken to obtain the usage characteristic matrix E, and the values ​​in the usage characteristic matrix E are fitted to obtain the usage characteristic value F; the 100-kilometer energy consumption characteristic matrix B is corrected using the characteristic value F to obtain the second target 100-kilometer energy consumption prediction matrix C2; according to the target 100-kilometer energy consumption prediction matrix, the current cruising range value or the predicted total cruising range of the target vehicle is obtained, and the target 100-kilometer energy consumption prediction matrix is ​​the first target 100-kilometer energy consumption prediction matrix C1 or the second target 100-kilometer energy consumption prediction matrix C2.

[0046] On the other hand, the present application also proposes a computer device, which includes a memory, a processor, and a processing program stored in the memory and executable on the processor. When the processing program is executed by the processor, the above-mentioned online prediction method for the cruising range of a new energy vehicle is implemented.

[0047] On the other hand, the present application further proposes a storage medium, on which a processing program is stored, and when the processing program is run by a processor, the above-mentioned online prediction method for the cruising range of a new energy vehicle is executed.

[0048] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0049] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0050] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A method for online prediction of the cruising range of new energy vehicles, characterized in that: The method comprises: Obtain vehicle condition data of multiple historical vehicles, and based on the vehicle condition data, calculate the average energy consumption per 100 kilometers of each historical vehicle at each preset SOH interval from the SOH start value to the preset SOH end value to form a 100-kilometer energy consumption matrix A; take a characteristic representative number for each column of the SOH value of the 100-kilometer energy consumption matrix A to form a 100-kilometer energy consumption characteristic matrix B; Obtain the battery pack SOH value of the target vehicle, and determine the relationship between the battery pack SOH value and the preset battery SOH value: If the battery pack SOH value is greater than or equal to the preset battery SOH value, the 100-kilometer energy consumption characteristic matrix B is used as the first target 100-kilometer energy consumption prediction matrix C1; If the battery pack SOH value is less than the preset battery SOH value, the average energy consumption per 100 kilometers of the target vehicle in each preset SOH interval from the SOH starting value to the SOH current value is counted to obtain a target energy consumption matrix D per 100 kilometers; the difference between the energy consumption characteristic matrix B per 100 kilometers and the target energy consumption matrix D per 100 kilometers is taken to obtain a usage characteristic matrix E, and the values ​​in the usage characteristic matrix E are fitted to obtain a usage characteristic value F; the energy consumption characteristic matrix B per 100 kilometers is corrected using the characteristic value F to obtain a second target energy consumption prediction matrix C2 per 100 kilometers; According to the target 100-kilometer energy consumption prediction matrix, the current cruising range value or the predicted total cruising range of the target vehicle is obtained, and the target 100-kilometer energy consumption prediction matrix is ​​the first target 100-kilometer energy consumption prediction matrix C1 or the second target 100-kilometer energy consumption prediction matrix C2.

2. The online prediction method for the cruising range of a new energy vehicle according to claim 1 is characterized in that: The vehicle condition data includes region, season, vehicle series, mileage, driving start and end time, battery pack voltage and current.

3. The online prediction method for the cruising range of a new energy vehicle according to claim 2 is characterized in that: According to the vehicle condition data, the step of calculating the average energy consumption per 100 kilometers of each historical vehicle at each preset SOH interval from the SOH start value to the preset SOH end value comprises: Determine the relationship between the mileage in the vehicle condition data and the preset mileage: If the mileage is less than the preset mileage, the vehicle condition data will be discarded; If the mileage is greater than or equal to the preset mileage, the vehicle condition data is used to classify the data by region, season, and vehicle series. The average energy consumption per 100 kilometers of each historical vehicle in each preset SOH interval from the SOH start value to the preset SOH end value is calculated according to the average energy consumption per 100 kilometers calculation formula. The average energy consumption per 100 kilometers calculation formula is: , Among them, u represents the average energy consumption per 100 kilometers, t1 and t0 represent the start and end time of driving respectively, V represents the battery pack voltage, I represents the battery pack current, and x represents the mileage.

4. The online prediction method for the cruising range of a new energy vehicle according to claim 3 is characterized in that: The preset SOH interval is 1%.

5. The online prediction method for the cruising range of a new energy vehicle according to claim 1 is characterized in that: When taking the characteristic representative number for each column of the SOH value of the 100-kilometer energy consumption matrix A, the median, mean, or standard deviation is used as the characteristic representative number.

6. The online prediction method for the cruising range of a new energy vehicle according to claim 1 is characterized in that: When fitting the values ​​in the characteristic matrix E to obtain the characteristic value F, the fitting calculation formula is F = (D - B) / B; When the eigenvalue F is used to correct the 100-kilometer energy consumption characteristic matrix B and obtain the second target 100-kilometer energy consumption prediction matrix C2, the corrected calculation formula is C2 = B * (1 + F).

7. The online prediction method for the cruising range of a new energy vehicle according to claim 1 is characterized in that: In the step of obtaining the current cruising range value or the predicted total cruising range of the target vehicle according to the target energy consumption prediction matrix per 100 kilometers, the current cruising range = (SOH×rated energy×SOC) / target energy consumption prediction value per 100 kilometers, and the total cruising range = (SOH×rated energy) / target energy consumption prediction value per 100 kilometers.

8. An online prediction system for the cruising range of new energy vehicles, characterized in that: The system comprises: A data acquisition module is used to acquire vehicle condition data of multiple historical vehicles; The data processing module is used to count the average energy consumption per 100 kilometers of each historical vehicle in each preset SOH interval from the SOH starting value to the preset SOH ending value according to the vehicle condition data, so as to form a 100-kilometer energy consumption matrix A; take the characteristic representative number of each column of the SOH value of the 100-kilometer energy consumption matrix A to form a 100-kilometer energy consumption characteristic matrix B; obtain the SOH starting value and the SOH current value of the target vehicle, and judge the size relationship between the SOH current value and the preset SOH ending value: A prediction module is used to use the 100-kilometer energy consumption characteristic matrix B as the first target 100-kilometer energy consumption prediction matrix C1 when the battery pack SOH value is greater than or equal to the preset battery SOH value; when the battery pack SOH value is less than the preset battery SOH value, the average 100-kilometer energy consumption of the target vehicle in each preset SOH interval from the SOH starting value to the host SOH current value is counted to obtain a target 100-kilometer energy consumption matrix D; the difference between the 100-kilometer energy consumption characteristic matrix B and the target 100-kilometer energy consumption matrix D is taken to obtain a usage characteristic matrix E, and the values ​​in the usage characteristic matrix E are fitted to obtain a usage characteristic value F; the 100-kilometer energy consumption characteristic matrix B is corrected using the characteristic value F to obtain a second target 100-kilometer energy consumption prediction matrix C2; according to the target 100-kilometer energy consumption prediction matrix, the current cruising range value or the predicted total cruising range of the target vehicle is obtained, and the target 100-kilometer energy consumption prediction matrix is ​​the first target 100-kilometer energy consumption prediction matrix C1 or the second target 100-kilometer energy consumption prediction matrix C2.

9. A computer device, characterized in that: The computer device includes a memory, a processor, and a processing program stored in the memory and executable on the processor. When the processing program is executed by the processor, an online prediction method for the cruising range of a new energy vehicle as described in any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: The storage medium stores a processing program, and when the processing program is executed by a processor, an online prediction method for the cruising range of a new energy vehicle as claimed in any one of claims 1 to 7 is implemented.